GDI / Document Intelligence & NLP Specialist

Advance Talent Solutions Incorporated; Boston (MA); On-site; USD 120,000 - 180,000; Part time

Benefits offered by this job

Flexible project-based consulting

Job summary

ATS+Partners is seeking a GDI/Document Intelligence & NLP Specialist to lead AI-driven extraction pipelines for invoices, certificates, health forms, and audit prep. You will design prompts, set up model ensembles, and manage HITL loops to maintain high accuracy on structured and unstructured documents.

You will architect classification, benchmarking, and continuous learning, collaborating with government or regulated-industry clients and leveraging Azure AI Document Intelligence and LangGraph

Qualifications

• 5+ years of AI/IDP implementation in production environments.
• Experience with confidence scoring and HITL design.
• Must provide benchmark results showing 80%+ extraction accuracy across unstructured documents.
• Two+ IDP deployments for government or regulated industries.
• Azure AI Document Intelligence (Form Recogniser): 2+ years hands-on configuration.

Responsibilities

• Design and configure AI extraction pipelines for four target workflows: Invoice Processing, Vehicle Insurance Certificate Reconciliation, Health Insurance Reconciliation, and Audit Preparation.
• Develop and maintain custom prompt templates for GPT-4o and Claude AI with JSON schemas and guidance.
• Configure LangGraph consensus and define confidence thresholds for HITL routing and review capture for retraining.
• Build and manage document classification taxonomy and validate accuracy on City document samples.
• Establish and execute accuracy benchmarking, hold-out test sets, and quarterly production audits.
• Lead prompt regression testing with annotated samples to detect accuracy regressions.
• Manage the continuous learning loop by exporting HITL corrections and updating models quarterly.
• Configure pre-processing settings: image quality, deskewing, segmentation, PDF/A normalization.

Skills

AI/IDP implementation

Confidence scoring

HITL design

RAG integration

Document classification

Model accuracy reporting

Python

Prompt engineering

LLM integration

Tools

Azure AI Document Intelligence

LangGraph

LangChain

ABBYY Vantage

Pinecone

GPT-4o

Claude AI

Job description

Boston, United States | Posted on 05/20/2026

ATS+Partners is seeking a GDI / DocumentIntelligence & NLP Specialist who brings verifiable, multi-year experienceimplementing Intelligent Document Processing and Generative DocumentIntelligence solutions — ideally for government or regulated-industry clients —with documented extraction accuracy benchmarks from prior deployments. Thisrole exists specifically to address the two most consequential gaps in thecurrent proposal:

• Minimum Criterion 1 requires five or more years ofexperience implementing AI Automation and GDI solutions, preferably formunicipal or government clients. The contractor’s own professional history mustprovide the concrete, dated implementation record that satisfies thisthreshold.
• Minimum Criterion 2 requires a proven ability toachieve 80%+ data extraction accuracy on unstructured documents. The contractormust be able to supply documented benchmark results from prior engagements —not theoretical capability claims — that an evaluator can verify.

The contractor will serve as the project's extraction engine expert, responsible for the design, configuration, andcontinuous improvement of all AI document extraction pipelines. They will ownprompt engineering for all four target workflows, configure the modelensemble’s consensus logic, build the field-level confidence scoring framework,and manage the human-in-the-loop feedback loop that drives continuous accuracyimprovement throughout the three-year contract term.

PRIMARY RESPONSIBILITIES

• Design and configure AI extraction pipelines for allfour target workflows: Invoice Processing, Vehicle Insurance CertificateReconciliation, Health Insurance Reconciliation, and Audit Preparation.
• Develop and maintain custom prompt templates for GPT-4oand Claude AI, including field extraction schemas in JSON format, field-levelinstructions with positive and negative examples, chain-of-thought validationprompts, and conditional extraction rules.
• Configure the LangGraph consensus orchestration layer:define how discrepancies between the two model outputs are resolved, whatconfidence thresholds trigger automatic pass-through vs. HITL routing, and howreviewer corrections are captured in graph state for retraining.
• Build and manage the document classification pipeline:design the taxonomy for audit document categorization, train or configure theclassifier against City document samples, and validate classification accuracy.
• Establish and execute the accuracy benchmarkingprotocol: define hold-out test sets for each workflow, run pre-pilot benchmarks, pilot accuracy benchmarks, and quarterly productionaccuracy audits.
• Lead prompt regression testing: maintain a library ofannotated sample documents that are re-run against every prompt update andmodel version change to detect accuracy regressions before they reachproduction.
• Manage the continuous learning loop: export reviewercorrections from the HITL queue, curate training data, coordinate modelfine-tuning or prompt updates on a quarterly basis.
• Configure pre-processing pipeline parameters: imagequality thresholds, deskewing settings, multi-page document segmentation rules,and PDF/A normalization parameters for each document type.
• Provide domain-specific extraction expertise for ACORDinsurance certificates, government invoices, AP aging schedules, GL trialbalances, and health insurance enrollment forms.
• Document all extraction schemas, prompt versions,confidence threshold configurations, and model accuracy results in aversion-controlled Model Registry maintained throughout the contract.

Requirements

• AI/GDIimplementation experience: 5+ years implementing Intelligent DocumentProcessing or Generative Document Intelligence solutions in productionenvironments
• Confidence scoringand HITL design: experience building tiered confidence routing logicconnecting AI extraction outputs to human review queues
• Documentedextraction accuracy benchmarks: must be able to provide benchmark results (with methodology) from at least two prior IDP deployments showing 80%+ field-level extraction accuracy on unstructured documents
• Government orregulated-industry IDP: at least two prior GDI/IDP implementations for government agencies, financial institutions, insurance carriers, orhealthcare organizations
• Azure AI DocumentIntelligence (Form Recogniser): 2+ years hands-on configuration of pre-builtand custom models for invoice, form, and certificate extraction
• Pre-processingpipeline: hands-on experience with PDF normalization, image quality scoring,deskewing, and format conversion as part of a production IDP pipeline
• LLM promptengineering: 2+ years designing structured extraction prompts for GPT-4o,Claude, or equivalent models, including JSON schema output, chain-of-thoughtprompting, and regression testing
• RAG integration:experience connecting LLM extraction pipelines to vector search (Azure AISearch, Pinecone, or equivalent) for cross-reference validation
• Documentclassification: experience training or configuring document classifiers formulti-category taxonomies in financial or government document environments
• Model accuracyreporting: ability to produce evaluator-grade benchmark reports withfield-level precision, recall, and F1 metrics

PREFERRED QUALIFICATIONS

• Massachusettsmunicipal or state government IDP experience: prior deployment of a documentintelligence solution for a Massachusetts city, town, or state agency(highest priority preference)
• LangGraph orLangChain: hands‑on experience building stateful multi-agent extractionworkflows with checkpointing and HITL interrupt/resume patterns
• Insurance documentexpertise: specific experience extracting from ACORD certificates ofinsurance, health insurance enrollment files, or explanation-of-benefitsdocuments
• Ensemblearchitecture: experience building multi-model consensus extraction systemswith model-specific confidence weighting
• Invoice and APdocument expertise: experience with multi-vendor invoice extraction includingedge cases (handwritten amounts, multi-page invoices, non-standard layouts)
• Audit documentexpertise: experience with trial balance extraction, GL account mapping, andfinancial work paper generation from source documents
• HIPAA-compliant AIpipelines: prior implementation of GDI solutions in HIPAA-governedenvironments, including PHI tokenization and BAA-covered model usage
• Fine-tuning andcontinuous learning: experience running RLHF-style feedback loops or few-shotfine-tuning on domain-specific document corpora
• ABBYY Vantage:experience configuring ABBYY for degraded scan processing alongside primaryAzure AI Document Intelligence pipeline
• Python:proficiency for custom extraction logic, pre-processing scripts, andbenchmarking tooling

Company Benefits for Contractors

• Flexible,project-based consulting opportunities with the ability to work across diversepublic, private, and nonprofit sector IT initiatives.
• Exposure tohigh-impact digital transformation, infrastructure modernization,cybersecurity, cloud, and AI-enabled projects that strengthen your portfolioand technical expertise.
• Collaborativepartnership model that values consultant input, innovation, and professionalautonomy while working alongside experienced client and project leadershipteams.
• Competitive contractor compensation with opportunities for repeatengagements, long-term client relationships, and expansion into strategicadvisory or technical leadership roles.